An Automated Script Classification System Using Structure Optimization with Firefly Algorithm

  • Authors

    • T. S. Suganya
    • Dr. S. Murugavalli
    2018-11-30
    https://doi.org/10.14419/ijet.v7i4.28.28350
  • Tamil Script Language, Handwritten Character Recognition, Neural Network (NN), Back Propagation (BP), Structure Optimization and Firefly Algorithm (FA),

  • The Tamil language is very ancient one with a very rich literature. Several writers used many different materials such as copper plates, mural paintings, conch shells, cloth, palm leaves, wood, and pottery, metal and stone for encrypting their writing. Any information that was gathered from such inscriptions has given us plenty of knowledge on education, administration, economic tax, religion, culture, history, and astronomy. All these epigraphical inscriptions have played a critical role in revealing the knowledge on past civilization and the character classification that belongs to the different time periods. This way, the system has been proposed for reading all ancient Tamil characters which belong to different periods by means of testing a very small amount of these characters in the Tamil language. All the characters that are examined have been obtained from the script and have been coordinated with all characters that belonged to the different periods by using machine intelligence. Thus, this system proposed contained several modules like the like segmentation, extraction of features, pre-processing, binarization, and acquisition of image, prediction, and classification of the script by employing the Artificial Neural Network (ANN). For this work, the metaheuristic algorithm inspired by nature called the Firefly Algorithm (FA) is introduced to train the ANN and to solve the problem of optimization. This FA has been based on the movements of the fireflies and their behaviour towards the light. For this, the behaviour of convergence and the performance of this proposed ANN training by using the FA has been analysed with the Back Propagation (BP) algorithm. The results of the simulation have proved the efficiency of computation in the process of training by making use of the technique of FA optimization.

     

     

  • References

    1. [1] Hamsaveni, L., Pradeep, C., & Chethan, H. K. (2017). Dimension Reduction For Script Classification-Printed Indian Documents. International Journal of Advanced Information Technology (IJAIT), 7 (3).

      [2] Obaidullah, S. M., Das, S. K., & Roy, K. (2013). A system for handwritten script identification from Indian document. Journal of Pattern Recognition Research, 8(1), 1-12.

      [3] Joshi, G. D., Garg, S., & Sivaswamy, J. (2007). A generalised framework for script identification. International Journal of Document Analysis and Recognition (IJDAR), 10(2), 55-68.

      [4] Greeba, M. J., & Bhuvaneswari, G. (2014). Recognition of Ancient Tamil Characters in Stone Inscription Using Improved Feature Extraction. international Journal of Recent Development in Engineering and Technology, 2(3).

      [5] Shanthi, N., & Duraiswamy, K. (2010). A novel SVM-based handwritten Tamil character recognition system. Pattern Analysis and Applications, 13(2), 173-180.

      [6] Vijayvergiya, D., & Pandey, A. (2015). A Classification Of Various Indian Script Recognition: A Survey. Jaipur International Journal of Converging Technologies and Management (IJCTM), 1 (2).

      [7] Obaidullah, S. K., Santosh, K. C., Halder, C., Das, N., & Roy, K. (2017). Word-level multi-script Indic document image dataset and baseline results on script identification. International Journal of Computer Vision and Image Processing (IJCVIP), 7(2), 81-94.

      [8] Chaudhari, S., & Gulati, R. M. (2016). Script identification using Gabor feature and SVM classifier. Procedia Computer Science, 79, 85-92.

      [9] Chaudhari, S. A., & Gulati, R. M. (2016). A Comparative Analysis of Feature Extraction Techniques and Classifiers Inaccuracies for Bilingual Printed Documents (Gujarati-English). International Journal of Applied Information Systems (IJAIS), 1.

      [10] Chacko, B. P., Krishnan, V. V., Raju, G., & Anto, P. B. (2012). Handwritten character recognition using wavelet energy and extreme learning machine. International Journal of Machine Learning and Cybernetics, 3(2), 149-161.

      [11] Prasetio, M. D., Hayashida, T., Nishizaki, I., & Sekizaki, S. (2017, November). Structural optimization of deep belief network theorem for classification in speech recognition. In Computational Intelligence and Applications (IWCIA), 2017 IEEE 10th International Workshop on (pp. 121-128). IEEE.

      [12] Kumar, S. V. K., & Poornima, T. V. (2014). An efficient period prediction system for Tamil epigraphical scripts using transductive support vector machine. Int. J. Adv. Res.¿ Comput. Commun. Eng, 3, 7999-8002.

      [13] Abubacker, N. F., & Raman, I. G. (2011). An approach for structural feature extraction for distorted tamil character recognition. International Journal of Computer Applications, 22(4), 24-28.

      [14] Pradeep, J., Srinivasan, E., & Himavathi, S. (2011, April). Diagonal based feature extraction for handwritten character recognition system using neural network. In Electronics Computer Technology (ICECT), 2011 3rd International Conference on (Vol. 4, pp. 364-368). IEEE.

      [15] Duan, Z., Wang, Y., & Xing, Y. (2015). Sound Quality Prediction of Vehicle Interior Noise under Multiple Working Conditions Using Back-Propagation Neural Network Model. Journal of transportation Technologies, 5(02), 134.

      [16] Chaudhari, G. U., & Mohanty, B. (2007). Function approximation using back propagation algorithm in artificial neural networks (Doctoral dissertation).

      [17] Yao, X. (1999). Evolving artificial neural networks. Proceedings of the IEEE, 87(9), 1423-1447.

      [18] Mandal, S., Saha, G., & Pal, R. K. (2015). Neural Network Training Using Firefly Algorithm. Global Journal on Advancement in Engineering and Science (GJAES), 1(1).

      [19] Gandomi, A. H., Yang, X. S., & Alavi, A. H. (2011). Mixed variable structural optimization using firefly algorithm. Computers & Structures, 89(23-24), 2325-2336.

  • Downloads

  • How to Cite

    S. Suganya, T., & S. Murugavalli, D. (2018). An Automated Script Classification System Using Structure Optimization with Firefly Algorithm. International Journal of Engineering & Technology, 7(4.28), 723-728. https://doi.org/10.14419/ijet.v7i4.28.28350